{"id":48854276,"url":"https://github.com/primaprashant/awesome-voice-typing","last_synced_at":"2026-04-15T11:38:07.078Z","repository":{"id":342769750,"uuid":"1175111451","full_name":"primaprashant/awesome-voice-typing","owner":"primaprashant","description":"Curated list of open-source speech-to-text and voice typing tools for Linux, macOS, Windows, Android, and iOS. Offline, local, and cloud.","archived":false,"fork":false,"pushed_at":"2026-04-11T05:03:38.000Z","size":39,"stargazers_count":90,"open_issues_count":0,"forks_count":11,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-11T05:10:07.061Z","etag":null,"topics":["ai","automatic-speech-recognition","awesome-list","dictation","dictation-tool","faster-whisper","linux","local-transcription","macos","offline-speech-recognition","open-source","parakeet","privacy-focused","push-to-talk","speech-to-text","transcription","voice-typing","whisper","whisper-cpp","wisprflow-alternative"],"latest_commit_sha":null,"homepage":"https://www.agenticcodingweekly.com/p/5-best-open-source-speech-to-text-tools-in-2026","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/primaprashant.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-07T08:40:41.000Z","updated_at":"2026-04-11T05:03:44.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/primaprashant/awesome-voice-typing","commit_stats":null,"previous_names":["primaprashant/awesome-voice-typing"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/primaprashant/awesome-voice-typing","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/primaprashant%2Fawesome-voice-typing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/primaprashant%2Fawesome-voice-typing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/primaprashant%2Fawesome-voice-typing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/primaprashant%2Fawesome-voice-typing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/primaprashant","download_url":"https://codeload.github.com/primaprashant/awesome-voice-typing/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/primaprashant%2Fawesome-voice-typing/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31840098,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-15T11:29:19.690Z","status":"ssl_error","status_checked_at":"2026-04-15T11:29:19.171Z","response_time":63,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","automatic-speech-recognition","awesome-list","dictation","dictation-tool","faster-whisper","linux","local-transcription","macos","offline-speech-recognition","open-source","parakeet","privacy-focused","push-to-talk","speech-to-text","transcription","voice-typing","whisper","whisper-cpp","wisprflow-alternative"],"created_at":"2026-04-15T11:38:06.072Z","updated_at":"2026-04-15T11:38:07.042Z","avatar_url":"https://github.com/primaprashant.png","language":null,"funding_links":[],"categories":["Other Lists"],"sub_categories":["Vue Lists"],"readme":"# Awesome Voice Typing\n\n[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen)](CONTRIBUTING.md)\n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue)](LICENSE)\n\nA curated list of open-source speech-to-text tools for voice typing and dictation across desktop, mobile, and CLI.\n\nThese tools let you speak and have text appear wherever you're typing. Some run speech-to-text entirely offline on your own hardware, others use cloud APIs, and many support both. All are open source.\n\n---\n\n## Contents\n\n- [Scope](#scope)\n- [Platform Snapshot](#platform-snapshot)\n- [Directory](#directory)\n- [Related Projects](#related-projects)\n- [Inclusion Notes](#inclusion-notes)\n- [Contributing](#contributing)\n- [License](#license)\n\n## Scope\n\nThis list focuses on tools that let you speak and get text into the place where you are actively working.\n\n- Open-source apps, keyboards, menu bar utilities, and CLI tools for dictation or voice typing\n- Desktop, mobile, and terminal-first workflows\n- Local-only and hybrid tools, as long as the project itself is open source\n\nThis list does not try to cover:\n\n- Closed-source products\n- General transcription tools that do not support typing or dictation workflows\n- Meeting bots, note takers, or speech APIs without a usable typing interface\n\n\u003cdetails\u003e\n\u003csummary\u003eBrowse by platform\u003c/summary\u003e\n\n- Linux: Buzz, Elograf, Epicenter Whispering, Handy, HNS, hyprwhspr, nerd-dictation, OpenWhispr, Speak to AI, Vibe, Vocalinux, Voquill, VOXD, VoxType, whisper_dictation, whisper-writer\n- macOS: Amical, Buzz, Epicenter Whispering, FluidVoice, FnKey, Ghost Pepper, Handy, HNS, OpenSuperWhisper, OpenWhispr, Pindrop, Tambourine Voice, TypeWhisper, Vibe, VoiceInk, VoiceTypr, Voquill, whisper-writer\n- Windows: Amical, Buzz, Chirp, Epicenter Whispering, Handy, HNS, OmniDictate, OpenWhispr, Tambourine Voice, Vibe, VoiceTypr, Voquill, whisper-writer\n- Android: Offline Voice Input, Transcribro, Whisper IME\n- iOS: WhisperBoard\n\n\u003c/details\u003e\n\nMost tools on this list support offline speech recognition. See `Mode` and `Engine` in the directory below for the details.\n\n## Directory\n\n`Mode`: `Local` means on-device speech recognition. `Hybrid` means the tool supports both local and cloud or BYO-cloud setups.\n\n| Name | Platforms | Mode | Engine | Summary |\n| --- | --- | --- | --- | --- |\n| [Amical](https://github.com/amicalhq/amical)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/amicalhq/amical?style=plastic\u0026label=%E2%98%85) | macOS, Windows | Local | Whisper | Context-aware dictation that adapts formatting to the app you are using. |\n| [Buzz](https://github.com/chidiwilliams/buzz)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/chidiwilliams/buzz?style=plastic\u0026label=%E2%98%85) | Linux, macOS, Windows | Local | Whisper, Whisper.cpp, Faster Whisper | Desktop app for microphone or file transcription; text stays in its own UI rather than typing into other apps. |\n| [Chirp](https://github.com/Whamp/chirp)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/Whamp/chirp?style=plastic\u0026label=%E2%98%85) | Windows | Local | Parakeet TDT | Dictates into Windows apps, runs on CPU only, and is aimed at locked-down corporate environments. |\n| [Elograf](https://github.com/papoteur-mga/elograf)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/papoteur-mga/elograf?style=plastic\u0026label=%E2%98%85) | Linux | Local | Vosk (via nerd-dictation) | GUI tray frontend for nerd-dictation with model switching and timeout controls. |\n| [Epicenter Whispering](https://github.com/EpicenterHQ/epicenter/tree/main/apps/whispering)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/EpicenterHQ/epicenter?style=plastic\u0026label=%E2%98%85) | Linux, macOS, Windows, Web | Hybrid | Whisper | Local-first dictation with a global shortcut and multiple Whisper providers; also available as a Chrome extension and web app. |\n| [FluidVoice](https://github.com/altic-dev/FluidVoice)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/altic-dev/FluidVoice?style=plastic\u0026label=%E2%98%85) | macOS | Hybrid | Parakeet, Apple Speech, Whisper | macOS dictation app that can type into any app and switch between local speech engines. |\n| [FnKey](https://github.com/evoleinik/fnkey)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/evoleinik/fnkey?style=plastic\u0026label=%E2%98%85) | macOS | Hybrid | Deepgram Nova-3, Groq Whisper | Rust menu bar app that activates the microphone only while holding Fn, with real-time streaming and batch cloud backends. |\n| [Ghost Pepper](https://github.com/matthartman/ghost-pepper)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/matthartman/ghost-pepper?style=plastic\u0026label=%E2%98%85) | macOS | Local | WhisperKit | Hold-to-talk menu bar dictation with local LLM cleanup of filler words; runs entirely on Apple Silicon. |\n| [Handy](https://github.com/cjpais/Handy)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/cjpais/Handy?style=plastic\u0026label=%E2%98%85) | Linux, macOS, Windows | Local | Whisper.cpp, Parakeet TDT | Shortcut-driven offline dictation built with Tauri and supporting several ASR model families. |\n| [HNS](https://github.com/primaprashant/hns)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/primaprashant/hns?style=plastic\u0026label=%E2%98%85) | Linux, macOS, Windows | Local | Faster Whisper | CLI tool that records from your mic, transcribes locally, and copies the result to the clipboard. |\n| [hyprwhspr](https://github.com/goodroot/hyprwhspr)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/goodroot/hyprwhspr?style=plastic\u0026label=%E2%98%85) | Linux | Hybrid | Whisper.cpp, Parakeet, BYOK cloud | Push-to-talk Linux dictation with a visualizer plus Waybar and systemd integration. |\n| [nerd-dictation](https://github.com/ideasman42/nerd-dictation)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/ideasman42/nerd-dictation?style=plastic\u0026label=%E2%98%85) | Linux | Local | Vosk | Hackable offline dictation that types into any window via simulated keystrokes. |\n| [Offline Voice Input (Android)](https://github.com/notune/android_transcribe_app)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/notune/android_transcribe_app?style=plastic\u0026label=%E2%98%85) | Android | Local | Parakeet TDT | Offline Android voice input keyboard with live subtitles and a privacy-first focus. |\n| [OmniDictate](https://github.com/gurjar1/OmniDictate)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/gurjar1/OmniDictate?style=plastic\u0026label=%E2%98%85) | Windows | Local | Whisper | Desktop dictation tool aimed at type-anywhere workflows. |\n| [OpenSuperWhisper](https://github.com/Starmel/OpenSuperWhisper)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/Starmel/OpenSuperWhisper?style=plastic\u0026label=%E2%98%85) | macOS | Local | Whisper, Parakeet | Native Swift menu bar dictation app optimized for Apple Silicon and global shortcuts. |\n| [OpenWhispr](https://github.com/OpenWhispr/openwhispr)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/OpenWhispr/openwhispr?style=plastic\u0026label=%E2%98%85) | Linux, macOS, Windows | Hybrid | Whisper.cpp, Parakeet, BYOK cloud | Cross-platform dictation with local models, optional cloud providers, and a custom dictionary. |\n| [Pindrop](https://github.com/watzon/pindrop)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/watzon/pindrop?style=plastic\u0026label=%E2%98%85) | macOS | Local | WhisperKit | Offline menu bar dictation app with optional AI-based transcript cleanup. |\n| [Speak to AI](https://github.com/AshBuk/speak-to-ai)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/AshBuk/speak-to-ai?style=plastic\u0026label=%E2%98%85) | Linux | Local | Whisper.cpp | Minimal Linux dictation tool that inserts text into the active window and can also run from the CLI. |\n| [Tambourine Voice](https://github.com/kstonekuan/tambourine-voice)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/kstonekuan/tambourine-voice?style=plastic\u0026label=%E2%98%85) | macOS, Windows | Hybrid | Faster Whisper, BYOK cloud | Voice interface for any app with configurable STT and LLM providers. |\n| [Transcribro](https://github.com/soupslurpr/Transcribro)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/soupslurpr/Transcribro?style=plastic\u0026label=%E2%98%85) | Android | Local | Whisper.cpp | Private and on-device speech recognition keyboard and service for Android. |\n| [TypeWhisper](https://github.com/TypeWhisper/typewhisper-mac)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/TypeWhisper/typewhisper-mac?style=plastic\u0026label=%E2%98%85) | macOS | Hybrid | Whisper (local and/or cloud) | Voice typing app with both local and cloud engine options. |\n| [Vibe](https://github.com/thewh1teagle/vibe)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/thewh1teagle/vibe?style=plastic\u0026label=%E2%98%85) | Linux, macOS, Windows | Local | Whisper.cpp | Desktop app to transcribe audio and video offline using OpenAI Whisper. |\n| [Vocalinux](https://github.com/jatinkrmalik/vocalinux)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/jatinkrmalik/vocalinux?style=plastic\u0026label=%E2%98%85) | Linux | Local | Whisper.cpp, Whisper, Vosk | Linux dictation with distro-specific setup guides and Vulkan acceleration notes. |\n| [VoiceInk](https://github.com/Beingpax/VoiceInk)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/Beingpax/VoiceInk?style=plastic\u0026label=%E2%98%85) | macOS | Hybrid | WhisperKit, BYOK | Native macOS dictation with per-app tuning, a custom dictionary, and optional commercial distribution. |\n| [VoiceTypr](https://github.com/moinulmoin/voicetypr)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/moinulmoin/voicetypr?style=plastic\u0026label=%E2%98%85) | macOS, Windows | Local | Whisper-based | Voice-to-text dictation built with Tauri; the repository is open source, but binaries require a one-time license purchase. |\n| [Voquill](https://github.com/josiahsrc/voquill)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/josiahsrc/voquill?style=plastic\u0026label=%E2%98%85) | Linux, macOS, Windows | Hybrid | Whisper.cpp, BYOK cloud | Cross-platform voice typing with a personal glossary and AI-assisted cleanup. |\n| [VOXD](https://github.com/jakovius/voxd)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/jakovius/voxd?style=plastic\u0026label=%E2%98%85) | Linux | Local | Whisper.cpp | Linux dictation with GUI, tray, and CLI modes plus optional LLM post-processing. |\n| [VoxType](https://github.com/peteonrails/voxtype)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/peteonrails/voxtype?style=plastic\u0026label=%E2%98%85) | Linux | Hybrid | Whisper.cpp, Parakeet, Moonshine, SenseVoice | Push-to-talk Linux dictation with seven engine choices, CJK support, and Wayland-optimized text insertion. |\n| [WhisperBoard](https://github.com/Saik0s/Whisperboard)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/Saik0s/Whisperboard?style=plastic\u0026label=%E2%98%85) | iOS | Local | Whisper.cpp | iOS app for recording speech and producing text with downloadable Whisper models. |\n| [Whisper IME](https://github.com/woheller69/whisperIME)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/woheller69/whisperIME?style=plastic\u0026label=%E2%98%85) | Android | Local | Whisper.cpp | Android keyboard and standalone app powered by Whisper, fully offline, and available on F-Droid. |\n| [whisper-writer](https://github.com/savbell/whisper-writer)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/savbell/whisper-writer?style=plastic\u0026label=%E2%98%85) | Linux, macOS, Windows | Hybrid | Faster Whisper, OpenAI API | Hotkey-driven dictation that auto-types into the active window with several recording modes. |\n| [whisper_dictation](https://github.com/themanyone/whisper_dictation)\u003cbr/\u003e\u003cbr/\u003e![stars](https://img.shields.io/github/stars/themanyone/whisper_dictation?style=plastic\u0026label=%E2%98%85) | Linux | Local | Whisper.cpp | Feature-rich Linux voice keyboard with dictation, voice commands, and webcam integration. |\n\n## Related Projects\n\nSpeech recognition engines, models, and APIs that power the tools listed above.\n\n- [Whisper](https://huggingface.co/collections/openai/whisper-release-6501bba2cf999715571c6b98) - OpenAI's ASR model weights; tiny through large, English-only and multilingual.\n- [whisper.cpp](https://github.com/ggml-org/whisper.cpp) - Pure C/C++ Whisper inference with zero dependencies; runs on Apple Silicon, CUDA, Vulkan, and WASM.\n- [Faster Whisper](https://github.com/SYSTRAN/faster-whisper) - CTranslate2-based Whisper reimplementation; up to 4x faster with lower memory.\n- [WhisperKit](https://github.com/argmaxinc/WhisperKit) - Swift package for on-device Whisper on Apple Silicon with streaming support.\n- [Parakeet](https://huggingface.co/collections/nvidia/parakeet-702d39a47302ef820e49839d) - NVIDIA's high-accuracy English ASR models in CTC, RNN-T, and TDT architectures.\n- [Vosk](https://github.com/alphacep/vosk-api) - Lightweight offline ASR with compact models, 20+ languages, and multi-language bindings.\n- [Apple Speech](https://developer.apple.com/documentation/speech) - Apple's on-device speech recognition framework for iOS, macOS, and watchOS.\n- [Awesome Whisper](https://github.com/sindresorhus/awesome-whisper) - Curated list of Whisper tools and resources.\n\n## Inclusion Notes\n\n- Entries are linked to their source repository rather than landing pages or app-store listings.\n- Some projects on this list also offer paid binaries or hosted features. They still belong here if the underlying repository is open source.\n- Submissions are held to a minimum maturity bar. See [CONTRIBUTING.md](CONTRIBUTING.md) before opening a PR.\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on adding, updating, or removing entries.\n\n## License\n\n[MIT](LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprimaprashant%2Fawesome-voice-typing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprimaprashant%2Fawesome-voice-typing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprimaprashant%2Fawesome-voice-typing/lists"}